gen_simmba: This function generates simulated multi-omics data.

In himelmallick/MimESys: Simulate Realistic Multi-Omics Datasets with Specified Structural and Sparsity Patterns

This function generates simulated multi-omics data.

Description

Generates simulated multi-omics datasets with specified parameters, including sample size, signal-to-noise ratio, DE probabilities, and response variable generation mode. It also splits the data into training and testing sets.

Usage

gen_simmba(
  nsample,
  snr = 1,
  p.train = 0.7,
  de.prob = rep(0.1, 3),
  de.downProb = rep(0.5, 3),
  de.facLoc = rep(1, 3),
  de.facScale = rep(0.4, 3),
  ygen.mode = "Friedman",
  nrep = 100,
  seed = 1234
)

Arguments

nsample	Sample size
snr	Signal to noise ratio
p.train	Train-test split ratio
de.prob	DE probability across all modalities
de.downProb	Down-regulation probability
de.facLoc	DE factor location
de.facScale	DE factor scale
ygen.mode	Y generation mode
nrep	Number of repetitions
seed	Random seed

Value

List containing training and testing datasets

Examples

simulated_data <- gen_simmba(nsample = 100)

himelmallick/MimESys documentation built on April 13, 2025, 9:06 p.m.